Show HN: Train Your Own Language Model on Your Favourite Programming Language
2 by rojasdiego | 0 comments on Hacker News.
In the context of the Deep Learning class at Tsinghua University, my teammates and I have trained our own (tiny) LLM on Go code using the `go/scanner` tokens as the tokenizer! If you're ever looking to train a single-GPU Language Model over the weekend on your favorite Programming Language, feel free to use our code and VSCode Extension.